JAVA+Selenium+Chrome+Chromedriver 模拟浏览器

linux 的环境准备

安装 google-chrome
yum install https://dl.google.com/linux/direct/google-chrome-stable_current_x86_64.rpm
下载 Chromedriver
地址：http://npm.taobao.org/mirrors/chromedriver/ （根据google-chrome -version找对应版本）
下载后放到根目录，注意要给 chromedriver 可执行权限：chmod 777 /chromedriver

windows 的环境准备

安装 google-chrome 浏览器
下载 Chromedriver
地址：http://npm.taobao.org/mirrors/chromedriver/ （根据google-chrome -version找对应版本）

JAVA Maven

maven 导入包
<dependency>
    <groupId>org.seleniumhq.selenium</groupId>
    <artifactId>selenium-java</artifactId>
    <version>2.33.0</version>
</dependency>

工具类例子

package c.o.v;

import org.apache.commons.lang3.StringUtils;
import org.openqa.selenium.By;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.chrome.ChromeDriver;
import org.openqa.selenium.chrome.ChromeOptions;

import java.util.Collections;
import java.util.HashMap;
import java.util.Map;

public class YXMUtil {

    public static void main(String[] args) {
        get("https://mall.q-gp.com/share/product?skuNo=366936136878081");
    }

    public static Map<String, String> get(String url) {
        // 参数配置
        System.setProperty("webdriver.chrome.driver", "/chromedriver.exe");
        WebDriver driver;
        ChromeOptions option = new ChromeOptions();
        option.addArguments("headless"); // 无界面参数
        option.addArguments("no-sandbox"); // 禁用沙盒
        // 通过ChromeOptions的setExperimentalOption方法，传下面两个参数来禁止掉谷歌受自动化控制的信息栏
        option.setExperimentalOptions("useAutomationExtension", false);
        option.setExperimentalOptions("excludeSwitches", Collections.singletonList("enable-automation"));
        driver = new ChromeDriver(option);
        driver.get(url);
        String title = "";
        String num = "";
        String img = "";
        long time = System.currentTimeMillis();
        while (StringUtils.isEmpty(img) || StringUtils.isEmpty(title) || StringUtils.isEmpty(num)) {
            img = driver.findElement(By.className("cr-image--img")).getAttribute("src");
            title = driver.findElement(By.className("title")).getText();
            num = driver.findElement(By.className("num")).getText();
            if (System.currentTimeMillis() - time > 5000) {
                System.out.println("获取超时，已结束");
                driver.quit();
                return null;
            }
            try {
                Thread.sleep(500);
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
        System.out.println("标题:" + title);
        System.out.println("价格:" + num);
        System.out.println("图片:" + img);
        driver.quit();
        Map<String, String> map = new HashMap();
        map.put("title", title);
        map.put("num", num);
        map.put("img", img);
        return map;
    }
}